Español

Explorar

Noticias de IA

22318 elementos — filtrados, clasificados y sin duplicados

Todos Models & Releases Research & Papers Funding & M&A Policy & Regulation Product Launches Industry Moves Developer Tooling Opinion & Editorial Security & Safety Other
arXiv cs.AI Research & Papers
ADORN: Adaptive Drift handling for Open RAN using Reinforcement Learning
arXiv cs.AI Research & Papers
Two Axes of LLM Abstention: Answer Correctness and Question Answerability
arXiv cs.AI Research & Papers
VEGAS: Human-Aligned Video Caption Evaluation via Gaze
arXiv cs.AI Research & Papers
The Context Access Divide: Interaction-Level Architecture as a Complementary Dimension of…
arXiv cs.AI Research & Papers
Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editi…
arXiv cs.AI Research & Papers
When the Judge Changes, So Does the Measurement: Auditing LLM-as-Judge Reliability
arXiv cs.AI Research & Papers
DocMaster: A Hierarchical Structure-Aware System for Document Analysis
arXiv cs.AI Research & Papers
SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduli…
arXiv cs.AI Research & Papers
When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities
arXiv cs.AI Research & Papers
UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing
arXiv cs.AI Research & Papers
WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search
arXiv cs.AI Research & Papers
ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation
arXiv cs.AI Research & Papers
Validity of LLMs as data annotators: AMALIA on authority
arXiv cs.AI Research & Papers
Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph
arXiv cs.AI Research & Papers
SLORR: Simple and Efficient In-Training Low-Rank Regularization
arXiv cs.AI Research & Papers
OpenCoF: Learning to Reason Through Video Generation
arXiv cs.AI Research & Papers
IFAR: Multi-Perspective and Multi-Level Causal Discovery with LLMs
arXiv cs.AI Research & Papers
Goal-Driven Reasoning in DatalogMTL with Magic Sets
arXiv cs.AI Research & Papers
A Vision Toward Energy-Efficient Domain-Specific Artificial Intelligence Models and Agents
arXiv cs.AI Research & Papers
MetaHGNIE: Meta-Path Induced Hypergraph Contrastive Learning in Heterogeneous Knowledge G…
arXiv cs.AI Research & Papers
SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Eva…
arXiv cs.AI Research & Papers
Conversational AI for Rapid Scientific Prototyping: A Case Study on ESA's ELOPE Competiti…
arXiv cs.AI Research & Papers
The Power of Power Law: Asymmetry Enables Compositional Reasoning
arXiv cs.AI Research & Papers
Accurate Portraits of Scientific Resources and Knowledge Service Components
arXiv cs.AI Research & Papers
Knowledge Graph and Accurate Portrait Construction of Scientific and Technological Academ…
arXiv cs.AI Research & Papers
The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based…
arXiv cs.AI Research & Papers
ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
arXiv cs.AI Research & Papers
Simulator Ensembles for Trustworthy Autonomous Driving Systems Testing
arXiv cs.AI Research & Papers
Concept-as-Tree: A Controllable Synthetic Data Framework Makes Stronger Personalized VLMs
arXiv cs.AI Research & Papers
Less Is More: Reducing Token Counts Without Compromising Performance